© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19199
    Prev
    Next
    INDEX
    Explanations

    */

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -with
    -0.09
    ленных
    -0.09
    -from
    -0.09
    ներից
    -0.08
    -exclusive
    -0.08
    િતા
    -0.08
    ленной
    -0.08
    合彩
    -0.08
    -host
    -0.08
    ixed
    -0.08
    POSITIVE LOGITS
     joku
    0.09
     qualc
    0.08
    ؟↵
    0.08
    ؟↵↵
    0.08
     index
    0.08
     qualcuno
    0.08
     taky
    0.08
    ?↵↵↵
    0.08
     People
    0.08
     jaka
    0.08
    Activations Density 0.002%

    No Known Activations